Messages in this thread | | | Subject | Re: [Bug #15192] netperf ~50% regression with 2.6.33-rc1, bisect to 1b9508f | From | Lin Ming <> | Date | Sat, 20 Feb 2010 15:52:57 +0800 |
| |
On Mon, 2010-02-01 at 16:04 +0800, Mike Galbraith wrote: > On Mon, 2010-02-01 at 01:22 +0100, Rafael J. Wysocki wrote: > > This message has been generated automatically as a part of a report > > of recent regressions. > > > > The following bug entry is on the current list of known regressions > > from 2.6.32. Please verify if it still should be listed and let me know > > (either way). > > Yes, it should remain open. We're currently waiting for some data from > Lin Ming. The regression itself isn't making much sense.. a kernel with > NEWIDLE disabled should show the same performance, but does not.
(sorry for late response, I'm just back from vacation)
We finally located this to a bug in mwait based C-state entry. Venki's patch has fixed it. http://patchwork.kernel.org/patch/78544/
Venki, this is the original report, http://marc.info/?l=linux-kernel&m=126441481427331&w=4
Thanks, Lin Ming
| |